© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15111
    Prev
    Next
    INDEX
    Explanations

    durations of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     särsk
    -0.95
    zegovina
    -0.92
     豪
    -0.90
     давно
    -0.89
     depuis
    -0.88
     уже
    -0.88
     already
    -0.85
     at
    -0.85
    jących
    -0.85
     también
    -0.84
    POSITIVE LOGITS
    mainly
    1.17
    Then
    1.16
    primarily
    1.07
     until
    1.06
    izate
    1.04
    ONLY
    1.02
    Either
    1.02
    either
    1.00
     Verpackung
    0.99
     Subsequently
    0.98
    Activations Density 0.032%

    No Known Activations